A Step-by-Step Guide To Detect Mobile Ad Fraud

0
78

According to the latest mobile ad fraud report of Appsflyer, mobile ad fraud is rising. Over the first quarter of 2018, mobile app marketers were exposed to 30% more fraud (as compared to the 2017 quarterly average), reaching $700-$800 million worldwide. It means fraudsters are getting more sophisticated. So, to beat them, you need to be more sophisticated, too.

There are different types of ad fraud from impression to post-install. The table below shows mobile ad fraud examples.

 

 

Fraud prevention requires the combination of technology, data, and people. The funnel from impression to post-install gives you important clues. So, you should learn how to read this funnel.

 

Know Your Enemy

 

There are many types of mobile ad frauds. They can manipulate impressions by serving invisible banners at a time and post-back event code that proves there is an app install even it didn’t normally as well as utilizing bots and “human farms” to carry out fraudulent actions like a click or install. So, you should not underestimate your enemy and know how broad its limits are.

 

Monitor Relevant Metrics

 

There are three important metrics to let you identify mobile ad fraud.

One of them is “time to install (TTI)”. Even though it depends on the internet speed and the app size, installing the app after the click takes more than 30 seconds generally. However, the common pattern of ad fraud shows that there are many installs completed within 10 seconds. So, keep track of TTI ratio very closely.

Another metric is “clicks to install (CTI)”. It shows you how many installs you have within a specific timeframe. This ratio makes the TTI ratio more meaningful. You can combine TTI and CTR ratios and spot outliers.

The last point you can look is the combination of IP address and User Agent. There could be a high number of app installs from the same IP on a given day. You can deduce it by analyzing IP addresses. However, IP addresses can be hidden. In such cases, the device’s User Agent gives you more deductive path. If a fraudster is more advanced that uses a Proxy, you need to focus on database work. Thanks to this analysis, you can explore IP mismatch, IP quality, and duplicate IPs.

 

Create A Pattern

 

It is a follow-up of monitoring relevant metrics. According to your output, you can draw a pattern systematically. For example, the time between the click and the install is significantly longer than for usual traffic. Or there are abnormally high levels of post-install events coming from a single publisher. You can determine a rule to emphasize there is an ad fraud.

 

Blacklist

 

Once you determine a pattern, your job gets ease off. You can add specific IPs and publishers to your blacklist for future reference. So, you can curate your own database comprising of blacklisted IPs and publishers.

 

Demand Transparency

 

Transparency means being able to access raw data. If you decide to work with the mobile ad fraud prevention tool, keep in mind that it is important to see clearly how well your mobile ad budget is being spent. So, ask for the complete transparency of your data in reporting, pricing, and ways of working.

 

Work With Trusted Partners

 

You can work with a trusted partner in the industry. As App Samurai, we use sophisticated machine-learning algorithms to help you detect, prevent, and fight against mobile ad fraud more systematically. Beside this, we are working on Interceptd which is a mobile fraud detection and prevention tool. Thanks to Interceptd, you can customize rulesets based on metrics such as Click-to-Install & Install-to-Event rates and blacklist and block sources automatically. As an advertiser, it lets you detect fraudulent traffic before click reaches to store page. As a publisher, it shows why/when a sub-publisher is blocked and sends automatic emails to notify publishers about blacklisted sources.




A Step-by-Step Guide To Detect Mobile Ad Fraud